Show Me How You Cite: Citation Fidelity, Usage, and Topology in the Evidence Behavior of AI Scientific Writing
Year: 2026
Type: conference-paper
Abstract: Large language models (LLMs) are increasingly used in scientific writing, yet their citation behavior remains poorly understood.We introduce CITESPECTRUM, a controlled dataset for analyzing citations across five levels of AI involvement, from LLM-Only generation to Human-Authored papers.Using citationbehavior features across fidelity, usage, and topology, we show that AI-generated papers differ from human-written papers in how citations are validated, grounded, used, and structurally organized.Even when retrieval and human guidance reduce ghost citations, AI-generated papers contain more unsupported claims, rely on front-section evidence, use citations more affirmatively, and form broader but less interconnected reference networks.Moreover, citation behavior alone enables a lightweight classifier to outperform strong text-based detectors, achieving 0.880 balanced accuracy and 0.944 AUROC.These results suggest that citation behavior provides a strong, interpretable signal of AI involvement beyond conventional textual patterns.The dataset is available at: https: //github.com/DISL-Lab/CiteSpectrum.
Institution: Korea Advanced Institute of Science and Technology
Language: English
Subfield: Statistics, Probability and Uncertainty
Field: Decision Sciences
Domain: Social Sciences
Open Access status: bronze
OpenAlex ID: W7224418893